cfzd / FcaNet

请问top里面的最优频率分量是不是只适用于77，一旦改变尺寸为4848 最优频率分量是否需要更换，还是仍起作用？请指点一下

@Lewis0427
我们目前的实验结果表明不需要更换，我们在COCO数据集（图像大小会变化）的网络也是一样使用7x7下的频率分量。可以参考一下这部分代码：

Lines 53 to 59 in aa5fb63

    
           x_pooled = x 
        
           if h != self.dct_h or w != self.dct_w: 
        
               x_pooled = torch.nn.functional.adaptive_avg_pool2d(x, (self.dct_h, self.dct_w)) 
        
               # If you have concerns about one-line-change, don't worry.   :) 
        
               # In the ImageNet models, this line will never be triggered.  
        
               # This is for compatibility in instance segmentation and object detection. 
        
           y = self.dct_layer(x_pooled)

好的知道了谢谢您

MultiSpectralDCTLayer类当中选择learnable random init，learnable DCT init和fixed DCT init，fixed random init会影响不同任务的效果吗？应该怎么选择呢？

@Lewis0427
如果你不是做实验探究这几个的区别的话，应该始终选择fixed DCT init.

	x_pooled = x
	if h != self.dct_h or w != self.dct_w:
	x_pooled = torch.nn.functional.adaptive_avg_pool2d(x, (self.dct_h, self.dct_w))
	# If you have concerns about one-line-change, don't worry. :)
	# In the ImageNet models, this line will never be triggered.
	# This is for compatibility in instance segmentation and object detection.
	y = self.dct_layer(x_pooled)

最优频率分量问题